© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 20352
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific word 'Ze' followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ze" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     behavi
    -0.89
     ancest
    -0.79
    Interstitial
    -0.75
    ials
    -0.74
     reconc
    -0.73
    IAL
    -0.70
     bullish
    -0.66
    ancial
    -0.66
     recre
    -0.65
     reluct
    -0.64
    POSITIVE LOGITS
    ze
    1.26
    lda
    1.20
    ppelin
    1.02
    ÅĤ
    1.00
    zes
    0.98
    ppe
    0.96
    zy
    0.93
    ggle
    0.89
    itsch
    0.88
    ppy
    0.86
    Activations Density 0.006%

    No Known Activations